Validation of the Measurement Process

Measurement Process," may be interpreted in two ways: In its usual usage, "validation" means "the de- termination of the degree of validity of a [meas...
0 downloads 0 Views 885KB Size
5 Optimization of Experimental Parameters in Chemical

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

Analysis STANLEY N. D E M I N G Department of Chemistry, University of Houston, Houston, TX 77004

The t i t l e of this symposium, "Validation of the Measurement Process," may be interpreted in two ways: In its usual usage, "validation" means "the determination of the degree of validity of a [measurement process]"(1). This definition suggests an activity that takes place after the measurement process has been developed. If the evaluation is successful, the process will receive o f f i c i a l sanction, confirmation, or approval. An alternate meaning of "validation" is "to make valid" in the sense of "producing the desired result" (2); that i s , making the measurement process meet the criteria against which i t is to be evaluated. This definition suggests activity that takes place while the measurement process is being developed. This latter interpretation has been emphasized by Youden (3) and is the interpretation I wish to stress here i f the i n i t i a l development of a measurement process is carried out with the goal of meeting the evaluation c r i t e r i a , then the probability that the process will receive rapid approval is greatly increased. SYSTEMS THEORY Figure 1 shows a systems theory view of the measurement process. The primary input to the system is a s amp1e. The measurement process abstracts the desi rë^inTormation from the sample and transforms the information into a number. This number, or result, is the primary output from the system. 162 In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

5.

DEMiNG

Experimental Parameters in Chemical Analysis

163

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

Ideally, the numerical value o f t h e output s h o u l d be r e l a t e d o n l y t o t h e d e s i r e d i n f o r m a t i o n i n the sample. As an example, a " p e r f e c t " measurement p r o c e s s f o r t h e a n a l y s i s o f enzyme a c t i v i t y w o u l d b e sensitive t o t h e amount o f enzyme i n t h e s a m p l e a n d i n s e n s i t i v e t o a l l other variables. In practice, the numerical value o f the output i s i n f l u e n c e d by a host o f other f a c t o r s . Some a r e associated with t h e sample m a t r i x , w h i l e o t h e r s app e a r as a d d i t i o n a l i n p u t s t o t h e measurement p r o c e s s . T h e s e f a c t o r s may b e s y s t e m a t i z e d a n d a r e shown s c h e m a t i c a l l y i n F i g u r e 1. An o b v i o u s c a t e g o r i z a t i o n o f t h e f a c t o r s a f f e c t i n g a measurement p r o c e s s i s t h e d i v i s i o n i n t o one set of factors t h a t a r e known t o h a v e a n e f f e c t o n the p r o c e s s ( s o l i d arrows) and a second s e t o f f a c tors that do a f f e c t t h e r e s u l t s o f t h e m e a s u r e m e n t p r o c e s s b u t have n o t y e t been i d e n t i f i e d - - that i s , they a r e unknown ( d a s h e d a r r o w s ) . Another grouping d i v i d e s the f a c t o r s i n t o those that are controlled (represented by a d o t on t h e t a i l o f t h e arrow) and those that are uncontrolled. When f a c t o r s a r e c a t e gorized i n these two ways, f o u r d i s t i n c t t y p e s r e sult : A factor that i s known t o e x e r t a s i g n i f i c a n t i n f l u e n c e on t h e r e s u l t o f a measurement process i s usually controlled. This w i l l u s u a l l y improve t h e p r e c i s i o n o f t h e method i f v a r i a t i o n s i n t h e uncontrolled factor level appear as n o i s e (that i s , t h e v a r i a t i o n s a r erapid with respect to the frequency o f measurement); i t might a l s o improve t h e accuracy o f the method i f t h e f r e q u e n c y o f c a l i b r a t i o n i s long with respect to variations i nthe uncontrolled factor level. Some factors a r e known t o i n f l u e n c e t h e r e s u l t of a measurement p r o c e s s b u t a r e l e f t uncontrolled. For example, i f a f a c t o r i s d i f f i c u l t o r e x p e n s i v e t o c o n t r o l and i f t h e f u n c t i o n a l r e l a t i o n s h i p o f i t s i n fluence i s known, t h e l e v e l o f t h i s f a c t o r m i g h t be measured and a c o r r e c t i o n a p p l i e d t o t h e r e s u l t . Or it might b e known t h a t a f a c t o r s i n f l u e n c e o n t h e r e s u l t , though r e a l , i s n o t s i g n i f i c a n t ; i t would p r o b a b l y be u n n e c e s s a r y t o c o n t r o l s u c h a f a c t o r . 1

Factors t h a t a r e unknown a n d c o n t r o l l e d a r e n o t u s u a l l y a p r o b l e m u n l e s s t h e method o f c o n t r o l i s i n -

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

V A L I D A T I O N OF

164

THE

MEASUREMENT

PROCESS

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

advertently changed. A f a m i l i a r example of a f a c t o r t h a t i s u n k n o w n and c o n t r o l l e d i s an impurity in a reagent: because the r e a g e n t i s always added i n a f i x e d amount, the l e v e l o f i m p u r i t y i s a l s o constant and is controlled. The e f f e c t s o f t h e r e a g e n t and t h e i m p u r i t y a r e c o n f o u n d e d and a r e u s u a l l y n o t s e p a ­ rated unless a change i n r e a g e n t l o t or s u p p l i e r i s made. Most unknown factors are u n c o n t r o l l e d . It is a s s u m e d t h a t f a c t o r s i n t h i s c a t e g o r y do n o t o r will not exert a significant influence. Whatever i n f l u ­ e n c e t h e y do e x e r t i s a c c e p t e d as " n o i s e " o r impreci­ sion. The s a m p l e c a n categories (_4) .

contain

RUGGEDNESS OF

factors

from a l l of

these

MEASUREMENT PROCESSES

As M a n d e l has p o i n t e d o u t , "The d e v e l o p m e n t o f a method of measurement i s to a l a r g e e x t e n t the d i s c o ­ very o f the most i m p o r t a n t e n v i r o n m e n t a l f a c t o r s and the s e t t i n g of t o l e r a n c e s f o r the v a r i a t i o n of each one o f t h e m " (4Γ) . T o l e r a n c e s make p o s s i b l e t h e o p e r ­ a t i o n a l i m p l e m e n t a t i o n of the concept of c o n t r o l : i t is o f t e n i m p o s s i b l e or i m p r a c t i c a l to c o n t r o l a f a c ­ t o r at a g i v e n l e v e l , but i t i s u s u a l l y p o s s i b l e and practical t o c o n t r o l a f a c t o r w i t h i n a s p e c i f i e d do­ main of f a c t o r l e v e l s - - t h a t i s , to c o n t r o l a factor around a given level, within specified tolerances. The s p e c i f i c a t i o n o f f a c t o r t o l e r a n c e s i s based upon the r e q u i r e d p r e c i s i o n o f t h e m e t h o d and a n s w e r s t h e q u e s t i o n , "To w h a t e x t e n t c a n a f a c t o r be a l l o w e d to vary before the output o f t h e s y s t e m c h a n g e s by v_ amount?" F o r a s p e c i f i e d v a l u e o f y, i t i s d e s i r a b l e that t h e s e t o l e r a n c e s be b r o a d so that the measurement p r o c e s s i s r e l a t i v e l y i n s e n s i t i v e to small v a r i a t i o n s in factor levels. To i l l u s t r a t e , c o n s i d e r t h e rela­ tionship b e t w e e n r e a c t i o n r a t e ( t h e r e s u l t o f a mea­ s u r e m e n t p r o c e s s ) as a f u n c t i o n o f pH (a known and controlled factor) f o r the k i n e t i c d e t e r m i n a t i o n of enzyme a c t i v i t y ( s e e F i g u r e 2 ) . In g e n e r a l , enzymes do n o t f u n c t i o n w e l l a t e x t r e m e s o f pH and e x h i b i t an o p t i m u m w i t h r e s p e c t t o pH. Let us assume that a method i s t o be d e v e l o p e d f o r m e a s u r i n g t h e a c t i v i t y o f an e n z y m e . A p e r f o r m a n c e c r i t e r i o n has b e e n spe-

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

5.

DEMiNG

Experimental Parameters in Chemical Analysis

i ν γ ν SAMPLE-

M

SYSTEM

-> R E S U L T

Figure 1. Systems theory view of the measurement process

Figu/e 2. Reaction rate as a function of pH for the kinetic determination of enzyme activity

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

165

166

V A L I D A T I O N O F T H E M E A S U R E M E N T PROCESS

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

cified that requires within y reaction rate

an i n t e r l a b o r a t o r y agreement units.

If t h e i n i t i a t i n g l a b o r a t o r y d e v e l o p s a method i n w h i c h t h e pH l e v e l i s s e t a t p o i n t A i n F i g u r e 2, then t h e i n t e r l a b o r a t o r y c o n t r o l o f pH m u s t b e e x ­ tremely t i g h t : s m a l l d i f f e r e n c e s i n pH b e t w e e n t h e laboratories e v a l u a t i n g t h e m e t h o d w i l l show up a s a large between-laboratory variance. Worse still, in the absence o f a d d i t i o n a l i n f o r m a t i o n , i t w o u l d be d i f f i c u l t t o s e p a r a t e pH a s o n e o f t h e c a u s e s o f t h i s variance. If, instead, the i n i t i a t i n g laboratory suggests a m e t h o d i n w h i c h t h e pH l e v e l i s s e t a t p o i n t Β in Figure 2, t h e n s m a l l d i f f e r e n c e s i n pH b e t w e e n t h e l a b o r a t o r i e s e v a l u a t i n g t h e method will contribute very l i t t l e to the between-laboratory variance. This method would have a h i g h e r p r o b a b i l i t y o f b e i n g ac­ cepted a f t e r i t s f i r s t i n t e r l a b o r a t o r y t e s t . Many o f t h e f a c t o r s a f f e c t i n g measurement pro­ c e s s e s e x h i b i t t h e b e h a v i o r shown i n F i g u r e 2. Other factors initially increase and then a s y m p t o t i c a l l y approach a p l a t e a u (e.g., t h e s u b s t r a t e dependence o f many enzymes). With f a c t o r s e x h i b i t i n g these types of behavior, a d j u s t i n g the f a c t o r l e v e l s t o improve the system o u t p u t w i l l a l s o improve t h e f a c t o r t o l e r ­ a n c e s (5) .

DEVELOPMENT OF MEASUREMENT PROCESSES The development o f a measurement p r o c e s s s h o u l d involve three stages: obtaining a response, improv­ ing t h e r e s p o n s e , and u n d e r s t a n d i n g t h e r e s p o n s e . Many l a b o r a t o r i e s c a r r y t h e development through the f i r s t stage o n l y . Youden (3) has p o i n t e d o u t t h e potential l i m i t a t i o n s o f s u c h m e t h o d s a n d h a s empha­ s i z e d t h e i m p o r t a n c e o f a c q u i r i n g an o p e r a t i o n a l un­ derstanding o f t h e measurement p r o c e s s e s ; t h a t i s , i d e n t i f y i n g and c o n t r o l l i n g those f a c t o r s that exert a significant effect on t h e s y s t e m . T h i s i s espe­ c i a l l y c r i t i c a l i f t h e measurement p r o c e s s e s are to become w i d e l y u s e d b y a number o f l a b o r a t o r i e s . The i m p r o v e m e n t o f r e s p o n s e h a s b e e n c a r r i e d o u t i n f r e q u e n t l y , a l t h o u g h i t s importance has been recog­ nized f o r some time. I n 1952 , B o x (6J) p r e s e n t e d a

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

5.

Experimental Parameters in Chemical Analysis

DEMiNG

167

p a p e r i n w h i c h i t was p o i n t e d o u t t h a t s i n g l e - f a c t o r at-a-time s t r a t e g i e s a r e inadequate f o r optimizing most chemical processes (.7,8_) a n d t h a t m e a s u r e m e n t processes (conceptually v e r y " s i m i l a r to production processes) c a n be e f f e c t i v e l y i m p r o v e d b y t h e u s e o f sequential f a c t o r i a l designs, a technique that later became known a s " e v o l u t i o n a r y o p e r a t i o n , " o r EVOP (9_, 10). EVOP s t r a t e g i e s a r e w e l l s u i t e d t o t h e i n d u s trial environment--the production process i s being run c o n s t a n t l y and p r o v i d e s a continuous framework for t h e l a r g e number o f e x p e r i m e n t s r e q u i r e d b y t h e sequential f a c t o r i a l designs. In the developmental l a b o r a t o r y , however, e f f i c i e n c y o f i n i t i a l experiment a t i o n i s s t r e s s e d a n d EVOP s t r a t e g i e s a r e l e s s d e s i rable. I n 1962, S p e n d l e y , H e x t , and H i m s w o r t h (11) i n t r o d u c e d t h e f i x e d s i z e s i m p l e x a s a more e f f i c i e n t sequential experimental design for t r a d i t i o n a l evolut i o n a r y o p e r a t i o n s ; L o n g (12) a p p e a r s t o have been the f i r s t t o a p p l y f i x e d s i z e s e q u e n t i a l s i m p l e x designs t o t h edevelopment o f measurement processes. Nelder a n d Mead (13) m o d i f i e d t h e s e q u e n t i a l s i m p l e x method t o a l l o w a c c e l e r a t i o n i n d i r e c t i o n s that are f a v o r a b l e and d e c e l e r a t i o n i n d i r e c t i o n s t h a t are unfavorable . We h a v e f o u n d t h e v a r i a b l e s i z e s i m p l e x ( s l i g h t l y m o d i f i e d ) t o b e a r a p i d means o f i m p r o v i n g r e s u l t s i n t h e development o f a n a l y t i c a l c h e m i c a l measurement processes (14-17). F a c t o r i a l d e s i g n s (18) , c e n t r a l composite d e s i g n s (19) , a n d B o x - B e h n k e n d e s i g n s ( 2 0 ) are u s e f u l f o r understanding the v a r i o u s f a c t o r ëTf e c t s upon t h e r e s p o n s e i n t h e r e g i o n o f t h e optimum.

EXAMPLE The d e t e r m i n a t i o n o f f o r m a l d e h y d e i n an aqueous sample c a n be d e t e r m i n e d by t h e a d d i t i o n o f chromotopic acid (4,5-dihydroxy-2,7-naphthalendisulfonic acid) and s u l f u r i c a c i d (21-25); a c o l o r develops, and t h e a b s o r b a n c e i s r e a d a t 570 nm. I n t h i s s t u d y ( 1 4 ) , a s a m p l e s i z e o f 2.00 m l was chosen. T h e amount o T a q u e o u s 20 g l " chromotropic acid (CTA, f a c t o r χι) a l l o w e d t o v a r y between 0.00 a n d 1.00 m l ; c o n c e n t r a t e d s u l f u r i c a c i d (H S0 , f a c t o r x ) c o u l d v a r y b e t w e e n 1.00 a n d 10.00 m l . T h e o b j e c t i v e s o f t h e study were: (a) t o determine t h e amounts o f H S 0 a n d CTA t h a t p r o d u c e d t h e g r e a t e s t a b s o r b a n c e f o r a g i v e n amount o f f o r m a l d e h y d e (2 ppm) 1

w

a

s

2

2

2

4

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

4

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

VALIDATION OF T H E M E A S U R E M E N T

PROCESS

7

I

1

0.1

1

0.2

1

1

ml o f

1

1

CTA

1

0.7

1

0.8

1

0.9

1

Analytica Chimica Acta

Figure 3. Simplex progress in the chromotropic acid-concentrated sulfuric acid domain. See text and Table 1 for details (14).

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

5.

Experimental Parameters in Chemical Analysis

DEMiNG

169

TABLE 1

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

Simplex

Vertex

progress

Retained

Chronotropic

Sulfuric

vertices

acid

a c i d (ml)

1

-

0. .200

2. .00

0. .221

2

-

0. , 7 8 0

2. .18

0. . 0 8 0

3

1,2

0. ,355

2. .68

0. .531

- 0 . , 224

2. .50

- 1 .. o o o

-

(ml)

Absorbance

4

1,3

0. . 5 2 9

2. .26

0. ,223

5'

-

0. . 684

2. .94

0. .197

5

3,4

0. .321

2. .23

0. . 3 2 5

6

3,5

0. .147

2, .65

0. .563

6'

-

- 0 . .044

2. .85

- 1 .. o o o

7

3,6

0. .182

3. . 0 9

0. .562

8'

-

- 0 . .027

3, .07

- 1 .. o o o

8

6,7

0. . 2 6 0

2, .77

0. . 5 7 3

9'

-

0. . 2 2 6

2. . 33

0. .502

9

6,8

0.. 1 9 3

2. . 9 0

0.. 5 9 9

10'

-

0. . 3 0 5

3, .03

0.. 5 7 0

11

8,9

0. . 1 8 7

2. .74

0. . 584

a

Primes indicate

rejected

b

b

b

vertices.

^Boundary v i o l a t i o n . R e p r i n t e d from r e f e r e n c e 14 w i t h p e r m i s s i o n

of

Elsevier

Scientific

P u b l i s h i n g Company.

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

VALIDATION OF T H E M E A S U R E M E N T

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

TABLE 2 Results

of factorial

experiments

Chronotropic

Sulfuric

acid

acid

(ml)

Absorbance

(ml)

0. 524

2., 50

0.,538 0.. 515

2..80

0., 516 0 . 526

3..10

0., 530 0..455

2.. 50

0.. 509 2..80

0..583

3..10

0., 534

0., 575

0..545 0.. 386

2.. 50

0..428 0.. 545

2..80

0..537 0..554

3,.10

0.. 551

Reiminted Elsevier

i n part

from r e f e r e n c e

Scientific

Publishing

14 w i t h p e r m i s s i o n o f

Company.

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

PROCESS

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

5.

DEMiNG

Experimental Parameters in Chemical Analysis

Analytica Chimica Acta

Figure 4.

Cell mean plot of factorial study (14)

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

171

172

VALIDATION OF THE MEASUREMENT PROCESS

TABLE 3

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

F a c t o r i a l analysis of variance

(ANOVA)

Source o f

Degrees o f

Sum o f

Mean

variation

freedom

squares

square

Chromotropic

2

0.00369

0.00179

6.27

98.0

2

0.01926

0.00963

33.66

99.9

4

0.01670

0.00417

14.59

99.9

0.00258

0.00029

F-ratio

Significance (%)

acid Sulfuric acid Interaction

Error

Reprinted

i n part

from r e f e r e n c e

Elsevier S c i e n t i f i c Publishing

14 w i t h p e r m i s s i o n o f

Company.

Analytica Chimica Acta

Figure 5. Absorbance response surface as a function of chromotropic acid volume, and concentrated sulfuric acid volume (14)

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

5.

DEMiNG

Experimental Parameters in Chemical Analysis

173

and (b) t o u n d e r s t a n d t h e e f f e c t s o f H S 0 a n d CTA upon t h e r e s p o n s e i n t h e r e g i o n o f t h e optimum so t h a t f a c t o r t o l e r a n c e s c o u l d be s p e c i f i e d .

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

2

4

Figure 3 shows t h e p r o g r e s s o f t h e s i m p l e x t o ­ ward t h e optimum ( d a t a i n T a b l e 1 ) . The numbers i n the f i g u r e i n d i c a t e t h e sequence i n which t h e r e t a i n ­ ed v e r t i c e s w e r e e v a l u a t e d ; r e j e c t e d v e r t i c e s a r e n o t shown. Table 2 contains ther e s u l t s o f a t h r e e - l e v e l two-factor, f u l l factorial study with replication c a r r i e d o u t i n t h e r e g i o n o f t h e s i m p l e x optimum; t h e r e s u l t s o f theanalysis o f variance are presented i n T a b l e 3. I n F i g u r e 4, c e l l means a r e p l o t t e d vs. CTA f o r each o f t h e three l e v e l s o f H2SO4. Other studies ( 2 5 ) h a v e shown t h a t t h e a b s o r ­ bance response i sr e l a t e d t o t h e r a t i o ( s u l f u r i c a c i d volume)/(total volume); this i s p r o b a b l y an e f f e c t caused by t h e heat o f m i x i n g w h i c h d r i v e s the reac­ tion toward completion. Assuming t h i s r e l a t i o n s h i p t o be a p p r o x i m a t e l y G a u s s i a n i n t h e r e g i o n o f t h e op­ timum, a model o f t h e form Absorbance = k ^ x p

[-( ( ( x / ( x + x 2

*(2.0/(x +x 1

+ 2

1

+ 2

2

2

2 . 0) ) - k ) ) / ( 2 k ) ] 2

2.0)) ( l - e x p f - k ^ ) )

can be f i t a n d i s v i s u a l i z e d i n t h e p s e u d o - t h r e e - d i ­ m e n s i o n a l p l o t shown i n Figure 5. The f a c t o r i a l p o i n t s a r e superimposed on t h e s u r f a c e . At l o w H2SO4 v o l u m e s , i n c r e a s i n g t h e volume o f CTA moves a c r o s s t h e " f r o n t " o f t h e r e s p o n s e surface with the r e s u l t that response decreases. A t an i n ­ t e r m e d i a t e l e v e l o f H^SO^, i n c r e a s i n g t h e v o l u m e o f CTA moves f r o m " b e h i n d " t h e d i a g o n a l r i d g e t o t h e t o p o f i t a n d down a g a i n o n t h e f r o n t s i d e . At the high­ est l e v e l o f H2SO4 s t u d i e d , i n c r e a s i n g t h e volume o f CTA moves a l o n g t h e " b a c k " o f t h e r i d g e w i t h t h e re­ s u l t that response increases. With t h i s o p e r a t i o n a l understanding o f a process f o r m e a s u r i n g t h e amount o f f o r m a l d e h y d e i n a n a q u e ­ ous sample, f a c t o r l e v e l s and f a c t o r t o l e r a n c e s can be s p e c i f i e d . Because c o n c e n t r a t e d H S0i+ i s a w o r r y some reagent, a n d b e c a u s e a q u e o u s CTA s o l u t i o n s o f accurate concentration aree a s i l y prepared and han­ dled, i t w o u l d b e a p p r o p r i a t e t o s p e c i f y a t i g h t CTA l e v e l o f 0.1 m l w h e r e t h e v o l u m e o f Η 5 0 has l e s s o f an e f f e c t . 2

2

4

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

174

VALIDATION

OF T H E MEASUREMENT

PROCESS

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

CONCLUSION The s t r a t e g y o f o b t a i n i n g a response, improving the response, and u n d e r s t a n d i n g t h e response i s a reasonable means o f o b t a i n i n g s o u n d m e a s u r e m e n t p r o ­ cesses. We h a v e f o u n d t h e v a r i a b l e size sequential s i m p l e x d e s i g n t o b e a n e f f i c i e n t means o f o p t i m i z i n g the primary response from a measurement process. Established s t a t i s t i c a l d e s i g n s a l l o w an understand­ ing o f t h e f a c t o r e f f e c t s and t h e i r interactions i n the r e g i o n o f t h e optimum.

ACKNOWLEDGMENTS The f o l l o w i n g have c o n t r i b u t e d t o t h e i d e a s and work p r e s e n t e d h e r e : P. G. K i n g , S. L. M o r g a n , L. R. Parker, J r . , A. S. O l a n s k y , a n d L. A. Y a r b r o . T h e author acknowledges support from t h e N a t i o n a l Science Foundation t h r o u g h g r a n t s GP-32911 a n d M P S - 7 4 - 2 3 1 5 7 .

LITERATURE CITED

1. "Webster's New Collegiate Dictionary," 1292, G. & C. Merriam Company, Springfield, MA, 1973. 2. "The Random House Dictionary of the English Lan­ guage, " 1578, Random House, New York, NY, 1969. 3. Youden, W. J., Materials Research & Standards (1961), 1, 862. 4. Mandel, J., "The Statistical Analysis of Experi­ mental Data," Interscience, New York, NY, 1964. 5. Skogerboe, R. Κ., in Baer, W. Κ., Perkins, A. J. and Grove, E. L., Eds., "Developments in Applied Spectroscopy," Vol. 6, 127, Plenum, New York, NY 1968. 6. Box, G. Ε. P . , Analyst (1952), 77, 879. 7. Box, G. E. P . , Biometrics (1954) 10, 16. 8. Morgan, S. L., and Deming, S. Ν . , Anal. Chem. (1974), 46, 1170. 9. Box, G. Ε. P . , Appl. Statist. (1957), 6, 81. 10. Box, G. Ε. P . , and Draper, Ν. R., "Evolutionary Operation," Wiley, New York, NY, 1969. 11. Spendley, W., Hext, G. R., and Himsworth, F. R., Technometrics (1962), 4, 441. 12. Long, D. E., Anal. Chim. Acta (1969), 46, 193. 13. Nelder, J. Α . , and Mead, R., Computer J. (1965), 7, 308.

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.

5.

DEMiNG

14. 15. 16.

Downloaded by KTH ROYAL INST OF TECHNOLOGY on August 31, 2015 | http://pubs.acs.org Publication Date: June 1, 1977 | doi: 10.1021/bk-1977-0063.ch005

17. 18. 19. 20. 21. 22. 23. 24. 25.

Experimental Parameters in Chemical Analysis

175

Olansky, A. S., and Deming, S. Ν . , Anal. Chim. Acta (1976), 83, 241. Morgan, S. L., and Deming, S. Ν . , J. Chromatogr. (1975), 112, 267. Parker, L. R., Morgan, S. L., and Deming, S. Ν . , Appl. Spectrosc. (1975), 29, 429. Deming, S. Ν . , and King, P. G . , Research/Devel­ opment (1974), 25(5), 22. Fisher, R. Α . , "The Design of Experiments," O l i ­ ver and Boyd, Edinburgh, 1935. Box, G. E. P . , and Wilson, Κ. B . , J. Royal Sta­ t i s t . Soc., Β (1951), 13, 1. Box, G. E. P . , and Behnkey, D. W., Ann. Math. Statist. (1960), 31, 838. Bricker, C. E., and V a i l , W. Α . , Anal. Chem. (1950), 22, 720. Klein, B . , and Weissman, Μ., Anal. Chem. (1953), 25, 771. Kamel, Μ., and Wizinger, R., Helv. Chim. Acta (1960), 43, 594. Sawicki, E., Hauser, T. R., and McPherson, S., Anal. Chem. (1962), 34, 1460. Houle, M. J., and Powell, R. L., Anal. Biochem. (1965), 13, 562.

In Validation of the Measurement Process; DeVoe, J.; ACS Symposium Series; American Chemical Society: Washington, DC, 1977.